-
ImportError: cannot import name 'EdgeConditionedConv' from 'spektral.layers' (/usr/local/lib/python3.8/dist-packages/spektral/layers/__init__.py)
ImportError: cannot import name 'batch_iterator' fr…
-
Is GraphMasking now redundant?
I am making modifications to my code based on the following recommendation: https://github.com/danielegrattarola/spektral/issues/283. However, some of this code no long…
-
Can I convert any previously loaded sdf file (using 'load_sdf') into networkx graph object in spektral?
Also, how to import GraphAttention and GlobalAttentionPool using spektral?
Not working =…
-
Hi, there are some updates to the Spektral's Convolutional layers:
A_in = Input(tensor=sp_matrix_to_sp_tensor(fltr)) will lead to failure
And GraphConv has been removed as well.
I will be r…
-
Hi, I am getting an error while trying to run deep_unsupervised_embedding on my project. I suspect there is some mismatch between the expected and received input shape for the CensNetConv network but …
-
for train_index, test_index in kfold.split(B, y1):
print('train_index',train_index)
print('test_index',test_index)
train_index, val_index = train_test_split(
train_index, tes…
-
**Spektral** certainly seems promising and easy to get started. Also, it has some good examples for predictive tasks. However, **Spektral** lacks examples of generative models.
_That said, other l…
-
After training step, I got a 'model' object . And then how to use it to predict new data?
I tried `model.predict([X, A],verbose=0)` and got some error
`InvalidArgumentError: Incompatible shapes:…
-
I am currently working on implementing graph neural networks using the Spektral package in Python. I am trying to include pooling layers (such as TopKPool) in my model, but I am running into dimension…
-
Dear Devs,
thank you for this library. I am currently writing my model using it, but I am a bit confused about the usage. I am working with sparse matrices but I find myself struggling with which typ…